Supporting Information Sharing in Loosely-Coupled Human Teamwork
People collaborate in carrying out such complex activities as treating patients, co-authoring documents and developing software. Technologies such as Google Drive, Dropbox and Github enable teams to share work artifacts remotely and asynchronously. The coordination of team members’ activities remains a challenge, however, because these technologies do not have capabilities for focusing people’s attention on the actions taken by others that matter most to their own activities. In this talk, I will present our work towards developing intelligent systems for supporting information sharing in distributed teams. Based on a study of complex health care teams, we formalize the problem of information sharing in loosely-coupled extended-duration teamwork. We develop a new representation, Mutual Influence Potential Networks, that implicitly learns collaboration patterns and dependencies among activities from team members’ interactions, and an algorithm that uses this representation to determine the information that is most relevant to each team member. Analysis of Wikipedia revision history data and an evaluation in a simulation environment demonstrate the ability of the proposed approach to identify relevant information to share with team members.
Joint work with Barbara Grosz and Krzysztof Gajos.a